Multi-Source Hard and Soft Information Fusion Approach for Accurate Cryptocurrency Price Movement Prediction

2024-09-27

arXiv.org

AI Summary

Cryptocurrency price prediction remains highly challenging due to extreme market volatility and intrinsic nonlinearity. To address this, we propose the Hard/Soft Information Fusion (HSIF) framework—a novel architecture that explicitly models dynamic interactions between hard information (e.g., technical indicators and historical price series) and soft information (e.g., social media sentiment). Specifically, FinBERT is employed to extract fine-grained sentiment features from financial text; a BiLSTM captures bidirectional temporal dependencies in time-series data; and a cross-modal feature alignment module coupled with a gated fusion mechanism integrates heterogeneous representations. Evaluated on Bitcoin price data, HSIF achieves 96.8% accuracy in directional movement prediction—outperforming unimodal baselines by 7.2–12.5 percentage points. This work establishes an interpretable and scalable paradigm for fusing multi-source, heterogeneous financial data, advancing both algorithmic design and practical forecasting in crypto markets.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust

Application Category

• Economics, Online Markets and Human Computation: Economic aspects of blockchain and cryptocurrencies
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

One of the most important challenges in the financial and cryptocurrency field is accurately predicting cryptocurrency price trends. Leveraging artificial intelligence (AI) is beneficial in addressing this challenge. Cryptocurrency markets, marked by substantial growth and volatility, attract investors and scholars keen on deciphering and forecasting cryptocurrency price movements. The vast and diverse array of data available for such predictions increases the complexity of the task. In our study, we introduce a novel approach termed hard and soft information fusion (HSIF) to enhance the accuracy of cryptocurrency price movement forecasts. The hard information component of our approach encompasses historical price records alongside technical indicators. Complementing this, the soft data component extracts from X (formerly Twitter), encompassing news headlines and tweets about the cryptocurrency. To use this data, we use the Bidirectional Encoder Representations from Transformers (BERT)-based sentiment analysis method, financial BERT (FinBERT), which performs best. Finally, our model feeds on the information set including processed hard and soft data. We employ the bidirectional long short-term memory (BiLSTM) model because processing information in both forward and backward directions can capture long-term dependencies in sequential information. Our empirical findings emphasize the superiority of the HSIF approach over models dependent on single-source data by testing on Bitcoin-related data. By fusing hard and soft information on Bitcoin dataset, our model has about 96.8% accuracy in predicting price movement. Incorporating information enables our model to grasp the influence of social sentiment on price fluctuations, thereby supplementing the technical analysis-based predictions derived from hard information.

Problem

• Predicting cryptocurrency price trends using AI
• Integrating quantitative indicators with social sentiment
• Improving accuracy through multisource fusion framework

Innovation

• Multisource fusion framework integrates quantitative and qualitative data
• Uses FinBERT for sentiment analysis and BiLSTM for sequential dependencies
• Combines financial indicators with social media sentiment signals